ElasticBERT: A pre-trained model with multi-exit transformer architecture.

ElasticBERT

This repository contains finetuning code and checkpoints for ElasticBERT.

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline

Xiangyang Liu, Tianxiang Sun, Junliang He, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

Requirements

We recommend using Anaconda for setting up the environment of experiments:

conda create -n elasticbert python=3.8.8
conda activate elasticbert
conda install pytorch==1.8.1 cudatoolkit=11.1 -c pytorch -c conda-forge
pip install -r requirements.txt

Pre-trained Models

We provide the pre-trained weights of ElasticBERT-BASE and ElasticBERT-LARGE, which can be directly used in Huggingface-Transformers.

  • ElasticBERT-BASE: 12 layers, 12 Heads and 768 Hidden Size.
  • ElasticBERT-LARGE: 24 layers, 16 Heads and 1024 Hidden Size.

The pre-trained weights can be downloaded here.

Model MODEL_NAME
ElasticBERT-BASE fnlp/elasticbert-base
ElasticBERT-LARGE fnlp/elasticbert-large

Downstream task datasets

The GLUE task datasets can be downloaded from the GLUE leaderboard

The ELUE task datasets can be downloaded from the ELUE leaderboard

Finetuning in static usage

We provide the finetuning code for both GLUE tasks and ELUE tasks in static usage on ElasticBERT.

For GLUE:

cd finetune-static
bash finetune_glue.sh

For ELUE:

cd finetune-static
bash finetune_elue.sh

Finetuning in dynamic usage

We provide finetuning code to apply two kind of early exiting methods on ElasticBERT.

For early exit using entropy criterion:

cd finetune-dynamic
bash finetune_elue_entropy.sh

For early exit using patience criterion:

cd finetune-dynamic
bash finetune_elue_patience.sh

Please see our paper for more details!

Contact

If you have any problems, raise an issue or contact Xiangyang Liu

Citation

If you find this repo helpful, we'd appreciate it a lot if you can cite the corresponding paper:

@article{liu2021elasticbert,
  author    = {Xiangyang Liu and
               Tianxiang Sun and
               Junliang He and
               Lingling Wu and
               Xinyu Zhang and
               Hao Jiang and
               Zhao Cao and
               Xuanjing Huang and
               Xipeng Qiu},
  title     = {Towards Efficient {NLP:} {A} Standard Evaluation and {A} Strong Baseline},
  journal   = {CoRR},
  volume    = {abs/2110.07038},
  year      = {2021},
  url       = {https://arxiv.org/abs/2110.07038},
  eprinttype = {arXiv},
  eprint    = {2110.07038},
  timestamp = {Fri, 22 Oct 2021 13:33:09 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2110-07038.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}
Owner
fastNLP
由复旦大学的自然语言处理(NLP)团队发起的国产自然语言处理开源项目
fastNLP
Similar Resources

Must-read papers on improving efficiency for pre-trained language models.

Must-read papers on improving efficiency for pre-trained language models.

Sep 11, 2022

The repository for the paper: Multilingual Translation via Grafting Pre-trained Language Models

Graformer The repository for the paper: Multilingual Translation via Grafting Pre-trained Language Models Graformer (also named BridgeTransformer in t

Aug 28, 2022

Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

Sep 16, 2022

Prompt-learning is the latest paradigm to adapt pre-trained language models (PLMs) to downstream NLP tasks

Prompt-learning is the latest paradigm to adapt pre-trained language models (PLMs) to downstream NLP tasks

Prompt-learning is the latest paradigm to adapt pre-trained language models (PLMs) to downstream NLP tasks, which modifies the input text with a textual template and directly uses PLMs to conduct pre-trained tasks. This library provides a standard, flexible and extensible framework to deploy the prompt-learning pipeline. OpenPrompt supports loading PLMs directly from huggingface transformers. In the future, we will also support PLMs implemented by other libraries.

Sep 22, 2022

Chinese Pre-Trained Language Models (CPM-LM) Version-I

CPM-Generate 为了促进中文自然语言处理研究的发展,本项目提供了 CPM-LM (2.6B) 模型的文本生成代码,可用于文本生成的本地测试,并以此为基础进一步研究零次学习/少次学习等场景。[项目首页] [模型下载] [技术报告] 若您想使用CPM-1进行推理,我们建议使用高效推理工具BMI

Sep 20, 2022

TweebankNLP - Pre-trained Tweet NLP Pipeline (NER, tokenization, lemmatization, POS tagging, dependency parsing) + Models + Tweebank-NER

TweebankNLP This repo contains the new Tweebank-NER dataset and Twitter-Stanza p

Aug 17, 2022

PyTorch Implementation of "Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging" (Findings of ACL 2022)

Feature_CRF_AE Feature_CRF_AE provides a implementation of Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging

Apr 29, 2022

Guide to using pre-trained large language models of source code

Guide to using pre-trained large language models of source code

Large Models of Source Code I occasionally train and publicly release large neural language models on programs, including PolyCoder. Here, I describe

Sep 23, 2022

A multi-voice TTS system trained with an emphasis on quality

TorToiSe Tortoise is a text-to-speech program built with the following priorities: Strong multi-voice capabilities. Highly realistic prosody and inton

Sep 21, 2022
BPEmb is a collection of pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) and trained on Wikipedia.

BPEmb is a collection of pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) and trained on Wikipedia. Its intended use is as input for neural models in natural language processing.

Sep 13, 2022
Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper

Data Augmentation using Pre-trained Transformer Models Code associated with the Data Augmentation using Pre-trained Transformer Models paper Code cont

Aug 22, 2022
Use PaddlePaddle to reproduce the paper:mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer
Use PaddlePaddle to reproduce the paper:mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer

MT5_paddle Use PaddlePaddle to reproduce the paper:mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer English | 简体中文 mT5: A Massively

Oct 17, 2021
KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)

KoGPT KoGPT (Korean Generative Pre-trained Transformer) https://github.com/kakaobrain/kogpt https://huggingface.co/kakaobrain/kogpt Model Descriptions

Sep 24, 2022
TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset.
TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset.

TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset. TunBERT was applied to three NLP downstream tasks: Sentiment Analysis (SA), Tunisian Dialect Identification (TDI) and Reading Comprehension Question-Answering (RCQA)

Sep 7, 2022
DziriBERT: a Pre-trained Language Model for the Algerian Dialect
DziriBERT: a Pre-trained Language Model for the Algerian Dialect

DziriBERT is the first Transformer-based Language Model that has been pre-trained specifically for the Algerian Dialect.

Sep 5, 2022
Google and Stanford University released a new pre-trained model called ELECTRA
Google and Stanford University released a new pre-trained model called ELECTRA

Google and Stanford University released a new pre-trained model called ELECTRA, which has a much compact model size and relatively competitive performance compared to BERT and its variants. For further accelerating the research of the Chinese pre-trained model, the Joint Laboratory of HIT and iFLYTEK Research (HFL) has released the Chinese ELECTRA models based on the official code of ELECTRA. ELECTRA-small could reach similar or even higher scores on several NLP tasks with only 1/10 parameters compared to BERT and its variants.

Sep 16, 2022
Code for CodeT5: a new code-aware pre-trained encoder-decoder model.
Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation This is the official PyTorch implementation

Sep 18, 2022
Implementation of Natural Language Code Search in the project CodeBERT: A Pre-Trained Model for Programming and Natural Languages.

CodeBERT-Implementation In this repo we have replicated the paper CodeBERT: A Pre-Trained Model for Programming and Natural Languages. We are interest

Jul 1, 2022
A simple recipe for training and inferencing Transformer architecture for Multi-Task Learning on custom datasets. You can find two approaches for achieving this in this repo.
A simple recipe for training and inferencing Transformer architecture for Multi-Task Learning on custom datasets. You can find two approaches for achieving this in this repo.

multitask-learning-transformers A simple recipe for training and inferencing Transformer architecture for Multi-Task Learning on custom datasets. You

Sep 25, 2022